Model save

README.md

@@ -2,14 +2,10 @@
 license: mit
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
 base_model: microsoft/phi-2
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: phi-2-gpo-test-iter-0
   results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # phi-2-gpo-test-iter-0
 
-This model is a fine-tuned version of [lole25/phi-2-sft-ultrachat-lora](https://huggingface.co/lole25/phi-2-sft-ultrachat-lora) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
 
 ## Model description
 

adapter_config.json

@@ -19,10 +19,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "dense",
+    "v_proj",
     "k_proj",
-    "v_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.6954,
+    "train_runtime": 3.6518,
     "train_samples": 30567,
-    "train_samples_per_second": 1.082,
-    "train_steps_per_second": 0.541
+    "train_samples_per_second": 1.095,
+    "train_steps_per_second": 0.548
 }

runs/Mar19_15-12-47_Braylon/events.out.tfevents.1710821619.Braylon.4042.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:705283880453457c15af25fac2672a643420df578369cf793eb6e67422270236
+size 5793

runs/Mar19_15-18-18_Braylon/events.out.tfevents.1710821955.Braylon.5247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe5f7fc46b6d57e6dbc5badf7337205b4391a9568f17af58aa6b4d4318ba39c
+size 5793

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 2.0,
     "train_loss": 2.5006682335515507e-05,
-    "train_runtime": 3.6954,
+    "train_runtime": 3.6518,
     "train_samples": 30567,
-    "train_samples_per_second": 1.082,
-    "train_steps_per_second": 0.541
+    "train_samples_per_second": 1.095,
+    "train_steps_per_second": 0.548
 }

trainer_state.json

@@ -27,9 +27,9 @@
       "step": 2,
       "total_flos": 0.0,
       "train_loss": 2.5006682335515507e-05,
-      "train_runtime": 3.6954,
-      "train_samples_per_second": 1.082,
-      "train_steps_per_second": 0.541
+      "train_runtime": 3.6518,
+      "train_samples_per_second": 1.095,
+      "train_steps_per_second": 0.548
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e572ae3c4aecda86cbf57a113c2abb725230f9d70070cc017f29bce06be9e77
+oid sha256:f93ed8083c90193aad25b1d03bfb42a33c9e715fb8e775056b6ba46679aab4e8
 size 5880